© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114553
    Prev
    Next
    INDEX
    Explanations

    freaked me out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hum
    -0.09
     distinguished
    -0.09
     Shim
    -0.09
    er
    -0.09
     dull
    -0.08
     Pere
    -0.08
     boring
    -0.08
     filthy
    -0.08
    Fc
    -0.08
    rage
    -0.08
    POSITIVE LOGITS
    -out
    0.17
     out
    0.15
     Out
    0.12
    -Out
    0.12
    _out
    0.12
    -outs
    0.12
    out
    0.12
    Out
    0.11
    anic
    0.11
     Ou
    0.10
    Activations Density 0.005%

    No Known Activations